DMCA
UNIT SELECTION IN A CONCATENATIVE SPEECH SYNTHESIS SYSTEM USING A LARGE SPEECH DATABASE (1996)
Cached
Download Links
| Citations: | 425 - 27 self |
BibTeX
@MISC{Hunt96unitselection,
author = {Andrew J. Hunt and Alan W. Black},
title = {UNIT SELECTION IN A CONCATENATIVE SPEECH SYNTHESIS SYSTEM USING A LARGE SPEECH DATABASE},
year = {1996}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
One approach to the generation of natural-sounding syn-thesized speech waveforms is to select and concatenate units from a large speech database. Units (in the current work, phonemes) are selected to produce a natural realisation of a target phoneme sequence predicted from text which is annotated with prosodic and phonetic context information. We propose that the units in a synthesis database can be considered as a state transition network in which the state occupancy cost is the distance between a database unit and a target, and the transition cost is an estimate of the quality of concatenation of two consecutive units. This framework has many similarities to HMM-based speech recognition. A pruned Viterbi search is used to select the best units for synthesis from the database. This approach to waveform synthesis permits training from natural speech: two meth-ods for training from speech are presented which provide weights which produce more natural speech than can be obtained by hand-tuning.
Keyphrases
large speech database natural speech pruned viterbi search transition cost target phoneme sequence synthesis permit synthesis database current work many similarity natural-sounding syn-thesized speech waveform natural realisation hmm-based speech recognition state transition network state occupancy cost consecutive unit database unit phonetic context information
